多任务学习论文趋势 2023–2026

共享表示

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 1,181 篇被归入该主题的论文。

主要结论

每年论文数

各会议论文数

按年份和会议统计

多任务学习论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
2023111435282288
202461315877227
2025101404776264
20261265791128402

代表论文

按年份和会议均匀挑选，方便快速看到每一届的样貌

全部多任务学习论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 402 篇，第 5 / 9 页

  1. ICML 2026CrossQ: Task-Aligned Cross-Token Conditional Quantization for Late Interaction Retrieval
  2. ICML 2026Dataset Distillation Efficiently Encodes Low-Dimensional Representations from Gradient-Based Learning of Non-Linear Tasks
  3. ICML 2026Decentralized Instruction Tuning: Conflict-Aware Splitting and Weight Merging
  4. ICML 2026DecodeShare: Tracing the Shared Subspace of LLM Decode-Time Decisions
  5. ICML 2026Decomposing the Basic Abilities of Large Language Models: Mitigating Cross-Task Interference in Multi-Task Instruct-Tuning
  6. ICML 2026Discretely-Refined Multi-view Clustering via Aligned Anchor Learning
  7. ICML 2026Distilling Linearized Behavior into Non-linear Fine-Tuning for Effective Task Arithmetic
  8. ICML 2026Distilling Task-Level Coordination Policies for Generalizable Multi-Agent Cooperation
  9. ICML 2026DITRON: Distributed Multi-level Tiling Compiler for Parallel Tensor Programs
  10. ICML 2026Dual-Calibration Multi-View Clustering via Compact Anchor Learning
  11. ICML 2026Efficient Training-Free Multi-Token Prediction via Embedding-Space Probing
  12. ICML 2026Evaluating and Steering Modality Preferences in Multi-modal LLMs
  13. ICML 2026FACT: Fuzzy Alignment with Comorbidity Topology for Reliable Multi-Label Medical Image Diagnosis
  14. ICML 2026Factored Latent Action World Models
  15. ICML 2026Feedback Control for Multi-Objective Graph Self-Supervision
  16. ICML 2026FiGuRO: Intrinsic Dimension Estimation for Multi-Modal Data
  17. ICML 2026Fine-Tune Once, Reuse Across Models: Bayesian Task-Update Factors and Approximations
  18. ICML 2026From 2D Grids to 1D Tokens: Reforming Shared Representations for Multimodal Image Fusion
  19. ICML 2026GCIB: Graph Contrastive Information Bottleneck for Multi-Behavior Recommendation
  20. ICML 2026Geometric Pocket-Centric Protein Encoding for Polypharmacology-Guided Multi-Target Drug Design
  21. ICML 2026Goal-Conditioned Agents that Learn Everything All at Once
  22. ICML 2026Gradient Descent with Large Step Size Restores Symmetry in Deep Linear Networks with Multi-Pathway
  23. ICML 2026HASTE: Hardware-Aware Dynamic Sparse Training for Large Output Spaces
  24. ICML 2026Hierarchical Anchor Graph Learning for Multi-View Clustering
  25. ICML 2026Hierarchical Representations for Cross-task Automated Heuristic Design using LLMs
  26. ICML 2026HyMTRL: A Hybrid Multi-Task Reinforcement Learning Framework via Phased Policy Evolution
  27. ICML 2026Hyperparameter Transfer Laws for Non-Recurrent Multi-Path Neural Networks
  28. ICML 2026Incomplete Multi-View Clustering via Neighborhood-Conditioned Diffusion
  29. ICML 2026Information-Theoretic Disentangled Latent Modeling with Conditional Diffusion for Incomplete Multi-View Clustering
  30. ICML 2026Intrinsic Task Symmetry Drives Generalization in Algorithmic Tasks
  31. ICML 2026Is Task-Specific Training Necessary for Anomaly Detection?
  32. ICML 2026Landmark-Guided Policy Optimization for Multi-Objective Language Model Selection
  33. ICML 2026Learn to Merge: Meta-Learning for Adaptive Multi-Task Model Merging
  34. ICML 2026Learning Generalized Label Distributions
  35. ICML 2026Learning to Extrapolate to New Tasks: A Relational Approach to Task Extrapolation
  36. ICML 2026LEMUR: Learned Multi-Vector Retrieval
  37. ICML 2026LiME: Lightweight Mixture of Experts for Efficient Multimodal Multi-task Learning
  38. ICML 2026MAGIC: Multi-Granularity Language-Informed Image Clustering
  39. ICML 2026Masked Multi-path Contrast with Confidence-Gated Semantic Imputation for Incomplete Multi-view Clustering
  40. ICML 2026MIMO-LP: A Multi-Input Multi-Output Framework for Subgraph-based Link Prediction
  41. ICML 2026MM-Spectrum: Multimodal Multi-spectral Molecular Structural Elucidation with a Stable MoE Framework
  42. ICML 2026Multi-Head Attention as a Source of Catastrophic Forgetting in MoE Transformers
  43. ICML 2026Multi-Task Bayesian In-Context Learning
  44. ICML 2026Multi-Task GRPO: Reliable LLM Reasoning Across Tasks
  45. ICML 2026Multi-task Linear Regression without Eigenvalue Lower Bounds: Adaptivity, Robustness, and Safety
  46. ICML 2026Multi-Way Representation Alignment
  47. ICML 2026Multimodal Fusion via Self-Consistent Task-Gradient Fields
  48. ICML 2026NBCG: Nash-Bargained Causal Game for Long-Tailed Multi-Label NLP
  49. ICML 2026Near-Optimal and Efficient First-Order Algorithm for Multi-Task Learning with Shared Linear Representation
  50. ICML 2026OPTION: Optimal Transport–Guided Flow Matching for Incomplete and Unaligned Multi-View Clustering

在 Claude、Cursor 里直接问这个趋势

接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。

可以直接复制这句话问 AI

用 paperlist 查多任务学习在 NeurIPS 2023–2026 的论文趋势，哪一年涨得最快？

AI 会调用的工具：get_topic_stats {"topic": "multi-task-learning"}

两分钟接入 Paperlist MCP（Claude Code、Cursor、Codex、ChatGPT）

常见问题

2023–2026 年四大会议一共有多少篇多任务学习论文？
共 1,181 篇，按年份分别是 2023 年 288 篇、2024 年 227 篇、2025 年 264 篇、2026 年 402 篇。
NeurIPS 2026 有多少篇多任务学习论文？
NeurIPS 2026 有 126 篇多任务学习论文，上一届是 101 篇。
ICLR 2026 有多少篇多任务学习论文？
ICLR 2026 有 57 篇多任务学习论文，上一届是 40 篇。
ICML 2026 有多少篇多任务学习论文？
ICML 2026 有 91 篇多任务学习论文，上一届是 47 篇。
CVPR 2026 有多少篇多任务学习论文？
CVPR 2026 有 128 篇多任务学习论文，上一届是 76 篇。
哪个会议的多任务学习论文最多？
NeurIPS，2023–2026 年共 399 篇。

「元学习与迁移」下的其他主题